This dataset can be used to test hallucinations in Retrieval-Augmented Generation (RAG) systems.It is based on: neural-bridge/rag-hallucination-dataset-1000
Data Instances
Each data point includes a context, a question about the context, and an answer.
A typical example looks like this:
{
"context": "...",
"question": "...",
"answer": "..."
}